ATL

Salary

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as sns

sns.set (style="white", color_codes=True)

%matplotlib inline

salaries = pd.read_csv("./Salaries.csv")

salaries.info()

salaries = pd.read_csv("./Salaries.csv")

salaries.info()

for col in ['BasePay', 'OvertimePay', 'OtherPay', 'Benefits']:

salaries[col] = pd.to_numeric(salaries[col], errors='coerce')

pay_columns = salaries.columns[3:salaries.columns.get_loc('Year')]

pay_columns

pays_arrangement = list(zip(*(iter(pay_columns),) * 3))

fig, axes = plt.subplots(2,3)

for i in range(len(pays_arrangement)):

for j in range(len(pays_arrangement[i])):

# pass in axes to pandas hist

salaries[pays_arrangement[i][j]].hist(ax=axes[i,j])

# axis objects have a lot of methods for customizing the look of a

plt

axes[i,j].set_title(pays_arrangement[i][j])

plt.show()

fig, axes = plt.subplots(2,3)

fig.set_figheight(5)

fig.set_figwidth(12)

for i in range(len(pays_arrangement)):

for j in range(len(pays_arrangement[i])):

# pass in axes to pandas hist

salaries[pays_arrangement[i][j]].hist(ax=axes[i,j])

axes[i,j].set_title(pays_arrangement[i][j])

# add a row of emptiness between the two r

ows

plt.subplots_adjust(hspace=1)

# add a row of emptiness between the cols

plt.subplots_adjust(wspace=1)

plt.show()

fig, axes = plt.subplots(2,3)

fig.set_figheight(5)

fig.set_figwidth(12)

for i in range(len(pays_arrangement)):

for j in range(len(pays_arrangement[i])):

salaries[pays_arrangement[i][j]].hist(ax=axes[i,j])

axes[i,j].set_title(pays_arrangement[i][j])

# set xticks with these labels,

axes[i,j].set_xticklabels(labels=axes[i,j].get_xticks(),rotation=30)

# with this rotation

plt.subplots_adjust(hspace=1)

plt.subplots_adjust(wspace=1)

plt.show()

IRIS

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as sns

sns.set (style="white", color_codes=True)

%matplotlib inline

df = pd.read_csv('iris.csv')

df.head()

df.info()

df['species'].value_counts()

df['sepal_length'].hist()

colors = ['red', 'green', 'blue']

species =['setosa','versicolor','virginica']

for i in range(3):

x = df[df['species']== species[i]]

plt.scatter(x['sepal_length'],x['sepal_width'], c = colors[i], label = species[i])

plt.xlabel("sepal_length")

plt.ylabel("sepal_width")

plt.legend()

sns.jointplot(x="sepal_length", y="sepal_width", data=df, height=5)

ax = sns.boxplot(x="species", y="petal_length", data=df)

ax = sns.boxplot(x="species", y="petal_length", data=df)

ax = sns.stripplot(x="species", y="petal_length", data=df, jitter=True,edgecolor="gray")

sns.violinplot(x="species", y="petal_length", data=df, height=6)

sns.FacetGrid(df, hue="species", height=6) \

.map(sns.kdeplot, "petal_length") \

.add_legend()

pd.plotting.andrews_curves(df, 'species');

from pandas.plotting import parallel_coordinates

parallel_coordinates(df, "species")

from pandas.plotting import radviz

radviz(df, "species")